Search papers, labs, and topics across Lattice.
3
0
3
11
Neglecting the structural differences in candidate negatives can lead to suboptimal recommendations, but SAHC-NS adapts to these variations, enhancing sample quality and model performance.
Missing modalities in federated learning can be effectively synthesized, leading to substantial performance gains in multimodal tasks.
By explicitly modeling the temporal decay of user-item interactions, TFPS constructs more reliable positive samples, leading to significant improvements in recommendation accuracy compared to methods that focus solely on negative sampling.
